Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1651 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.5010. Min Act: -0.1700
Data Index: 729742 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.3760. Min Act: -0.1700
Data Index: 931226 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.3760. Min Act: -0.1700
Data Index: 584856 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.2822. Min Act: -0.1700
Data Index: 260593 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.2509. Min Act: -0.1700
Data Index: 44358 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.2197. Min Act: -0.1700
Data Index: 817624 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.2197. Min Act: -0.1700
Data Index: 1279476 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.2509. Min Act: -0.1700
Data Index: 179488 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1572. Min Act: -0.1700
Data Index: 905799 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.2509. Min Act: -0.1700
Data Index: 1159418 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.2197. Min Act: -0.1700
Data Index: 560943 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1572. Min Act: -0.1700
Data Index: 162607 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0946. Min Act: -0.1700
Data Index: 58683 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0946. Min Act: -0.1700
Data Index: 394528 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1259. Min Act: -0.1700
Data Index: 1276789 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1259. Min Act: -0.1700
Data Index: 1189673 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0634. Min Act: -0.1700
Data Index: 895400 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0946. Min Act: -0.1700
Data Index: 926520 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.1259. Min Act: -0.1700
Data Index: 645102 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5010. Min Range: -4.5010
Max Act: 4.0946. Min Act: -0.1700
Data Index: 253987 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19